This is a guide to get started with Botium Coach.
Step 1: Connect Botium Coach to Your Conversational AI
Step 2: Prepare Datasets for Training and Testing
This is the step where most of the effort is involved: the machine learning algorithms involved in NLP - and most of the state-of-the-art NLP engines out there are based on some kind of machine learning - are only as good as the data they have been trained on. It is both a question of quality as well as quantity.
Step 3: Start a Test Session on Botium Box
In the previous steps, we connected Botium Box with your NLU engine and prepared the test dataset. In this step we will start the first test session.
Step 4: Identify NLP-related Issues and Solutions
The Botium Coach Dashboard visualizes the NLP performance metrics and suggests steps for improving it. It will show any pieces of test data that either did not return the expected intent, did return the expected intent but with a low confidence score, or did return the expected intent, but with a confidence score close to another intent’s.
Step 5: Annotate and Augment Training Dataset
As you have now identified some issues in your NLU performance it is time to augment the training data to improve the NLU performance.
Step 6: Training your NLU engine
For your convenience and for fast feedback cycles, Botium Box brings a Test Case Wizard for uploading training data from Botium Box to your NLU engine of choice and start the training process.
Step 7: Validate Improvements
Parent topic: NLU / NLP Testing
Please sign in to leave a comment.